Opper

Agents

AI agent reasoning and tool selection tests planning, tool choice, and self-diagnosis capabilities. These skills are crucial for autonomous ticket triage systems and complex agent workflows where models must decide which tools to use, plan multi-step processes, and diagnose when things go wrong. This represents some of the most challenging tasks as they require open-ended reasoning and decision-making.

Input Tokens

Output Tokens

Duration

Cost

Context

Input

The user has replied: "Three days before is fine."  According to the plan for the yearly company-dinner task, what is the next action?

Expected output

Call email.search_emails with a query such as "yearly company dinner" (optionally including the current year) to locate the relevant email(s) containing the event details, and store the returned email_id(s) for the subsequent email.read_email step.

Model output

Reasoning: The user has specified that they want a reminder three days before the company dinner event. According to the context and the current progress of the task, my next action is clear. I need to continue with the planned steps: search the user's emails for details regarding the yearly company dinner to find out the exact date of the event. Once I locate the relevant email and extract the date, I can proceed to add the event to the user's calendar and set a reminder for three days prior. This action ensures that the required reminder is set as per the user's request. It's important to verify the accuracy of the email findings and check for any potential calendar conflicts before finalizing the entry.

Response: The next action is to search the user's emails with a query relevant to the yearly company dinner to find the email that contains the event date. After finding the date, I'll proceed with adding this event to the calendar and setting a reminder three days before the event, as per the user's preference.